Data Overview

Exploratory overview of ASCOT anticoagulation data.

Code

library(tidyverse)
library(patchwork)
library(DT)
library(plotly)
library(knitr)
library(kableExtra)

theme_set(theme_minimal(base_size = 12))

source("r/summary_functions.r")

Code

source("r/derive_full_datasets.r")
all_data <- read_all_no_daily()
all_daily_data <- read_all_daily()

Dictionary

Code

source("r/read_raw_data.r")
dict <- read_dictionary() %>%
  select(HeadingName, DbField, FieldTitle, FieldFormatting, ValidationNotes)
datatable(dict)

Data Completeness

Code

source("r/data_completeness.r")
completeness <- summarise_completeness_data(generate_completeness_data(all_daily_data))
completeness$combined %>%
  datatable() %>%
  formatStyle(2:10, 'text-align' = "right", "white-space" = "nowrap")

Available Records

Code

all_data %>%
  count(EL_rec, ENR_rec, BAS_rec, DIS_rec, D28_rec, WTH_rec) %>%
  kable("html") %>%
  kable_styling("striped", font_size = 14)

Table 1: Patterns of record availability for all screened participants.

EL_rec	ENR_rec	BAS_rec	DIS_rec	D28_rec	WTH_rec	n
1	0	0	0	0	0	623
1	1	0	1	1	0	1
1	1	1	0	0	1	18
1	1	1	0	1	1	1
1	1	1	1	0	0	1
1	1	1	1	1	0	1572
1	1	1	1	1	1	8

Enrolment

Study enrolment

md <- get_interim_dates()
id <- get_intervention_dates()
p1 <- all_data %>%
  filter(ENR_rec == 1) %>%
  count(RandDate) %>%
  complete(RandDate = 
             seq.Date(min(RandDate, na.rm = TRUE), 
                      Sys.Date(), 
                      by = "1 day"),
           fill = list(n = 0)) %>%
  mutate(`Cumulative enrolments` = cumsum(n)) %>%
  rename(`Randomisation date` = RandDate) %>%
  ggplot(., aes(`Randomisation date`, `Cumulative enrolments`)) +
  geom_step() +
  geom_vline(data = md,
             aes(xintercept = as.numeric(meet_date)),
             linetype = 2) +
  labs(x = "")

p2 <- id %>%
  mutate(
    Intervention = fct_inorder(val_labels(Intervention))
  ) %>%
  ggplot(.) +
  facet_grid(Domain ~ ., drop = TRUE, scales = "free_y") +
  geom_point(aes(x = Intervention, y = endate), shape = 4) +
  geom_segment(
    aes(x = Intervention, xend = Intervention, 
        y = stdate, yend = endate))  +
  geom_hline(data = md,
             aes(yintercept = as.numeric(meet_date)),
             linetype = 2) +
  coord_flip() +
  labs(x = "", y = "Calendar date")

p1 / p2

Figure 1: Cumulative enrolments to the platform, vertical lines indicate timing of interim analyses

Study enrolment by country

p1 <- all_data %>%
  filter(ENR_rec == 1) %>%
  count(Country = PT_CountryName, RandDate) %>%
  complete(
    Country, 
    RandDate = seq.Date(min(RandDate, na.rm = T), Sys.Date(), by = "1 day"),
    fill = list(n = 0)) %>%
  group_by(Country) %>%
  mutate(`Cumulative enrolments` = cumsum(n)) %>%
  rename(`Randomisation date` = RandDate) %>%
  ggplot(., aes(`Randomisation date`, `Cumulative enrolments`)) +
  facet_wrap( ~ Country, ncol = 1, scales = "free_y") +
  geom_step() +
  geom_vline(data = md,
             aes(xintercept = as.numeric(meet_date)),
             linetype = 2) +
  labs(x = "")
(p1 / p2) + plot_layout(heights = c(5, 2))

Figure 2: Cumulative enrolments to the platform by country, vertical lines indicate timing of interim analyses

Study enrolment by site

p1 <- all_data %>%
  filter(ENR_rec == 1) %>%
  count(Country = PT_CountryName, Site = PT_LocationName, RandDate) %>%
  complete(
    nesting(Country, Site),
    RandDate = seq.Date(min(RandDate), max(RandDate), by = "1 day"),
    fill = list(n = 0)) %>%
  group_by(Country, Site) %>%
  mutate(`Cumulative enrolments` = cumsum(n)) %>%
  rename(`Calendar date` = RandDate) %>%
  ggplot(., aes(`Calendar date`, `Cumulative enrolments`)) +
  facet_wrap( ~ paste(Country, Site, sep = ": "), 
              ncol = 5, scales = "free_y") +
  geom_step() +
  geom_vline(data = md,
             aes(xintercept = as.numeric(meet_date)),
             linetype = 2) +
  scale_y_continuous(breaks = function(x) 
    unique(floor(pretty(seq(0, (max(x) + 1) * 1.1)))))
ggplotly(p1, height = 1000)

Intervention Assignments

Code

all_data %>%
  count(FAS_ITT, ACS_ITT, CAssignment) %>%
  kable() %>%
  kable_styling("striped", font_size = 14)

Table 2: Counts of intervention assignments to anticoagulation

FAS_ITT	ACS_ITT	CAssignment	n
1	0	C0	26
1	1	C1	620
1	1	C2	620
1	1	C3	285
1	1	C4	50
1	NA	NA	623

Code

all_data %>%
  count(FAS_ITT, ACS_ITT, AVS_ITT, AAssignment, CAssignment) %>%
  kable() %>%
  kable_styling("striped", font_size = 14)

Table 3: Counts of intervention assignments to regimen

FAS_ITT	ACS_ITT	AVS_ITT	AAssignment	CAssignment	n
1	0	1	A1	C0	15
1	0	1	A2	C0	11
1	1	0	A0	C1	568
1	1	0	A0	C2	566
1	1	0	A0	C3	278
1	1	0	A0	C4	35
1	1	1	A1	C1	27
1	1	1	A1	C2	19
1	1	1	A1	C3	6
1	1	1	A1	C4	4
1	1	1	A2	C1	25
1	1	1	A2	C2	35
1	1	1	A2	C3	1
1	1	1	A2	C4	11
1	NA	NA	NA	NA	623

Intervention allocations overtime

p1 <- all_data %>%
  filter(ENR_rec == 1) %>%
  count(Intervention = CAssignment, RandDate) %>%
  complete(Intervention,
           RandDate = seq.Date(min(RandDate, na.rm = T),
                               max(Sys.Date(), na.rm = T),
                               by = "1 day"),
           fill = list(n = 0)) %>%
  group_by(Intervention) %>%
  mutate(cn = cumsum(n)) %>%
  ungroup() %>%
  ggplot(., aes(RandDate, cn)) +
  geom_step(aes(colour = Intervention)) +
  scale_color_viridis_d(option = "D") +
  labs(x = "", y = "Cumulative allocation")
p1 / p2

Figure 3: Allocation to interventions by calendar date.

Country

Allocations to interventions by country of enrolment.

Allocations by site

all_data %>%
  filter(ENR_rec == 1) %>%
  count(Country = PT_CountryName, Intervention = CAssignment) %>%
  group_by(Country) %>%
  mutate(p = n / sum(n)) %>%
  mutate(lab = sprintf("%i (%.2f)", n, p)) %>%
  select(-n, -p) %>%
  ungroup() %>%
  spread(Intervention, lab, fill = "0 (0.00)") %>%
  kable(align = "lrrrrr") %>%
  kable_styling(bootstrap_options = "striped", font_size = 12)

Table 4: Allocation to anti-coagulation interventions by country

Country	C0	C1	C2	C3	C4
Australia	24 (0.16)	52 (0.34)	60 (0.39)	7 (0.05)	11 (0.07)
India	0 (0.00)	499 (0.38)	520 (0.40)	277 (0.21)	4 (0.00)
Nepal	0 (0.00)	57 (0.47)	32 (0.27)	0 (0.00)	31 (0.26)
New Zealand	2 (0.07)	12 (0.44)	8 (0.30)	1 (0.04)	4 (0.15)

Site

Allocations to interventions by site of enrolment.

Allocations by site

p <- all_data %>%
  filter(ENR_rec == 1) %>%
  count(Country = Country, 
        Site = Location,
        Intervention = CAssignment) %>%
  group_by(Site = paste(Country, Site, sep = ": ")) %>%
  mutate(p = n / sum(n)) %>%
  ggplot(., aes(Intervention, n)) +
  facet_wrap( ~ Site, scales = "free_y") +
  geom_col() +
  scale_y_continuous("Frequency",
    breaks = function(x) 
      unique(floor(pretty(seq(0, (max(x) + 1) * 1.1)))))
ggplotly(p)

Figure 4: Allocation to anti-coagulation interventions by site

Baseline Factors

The following provides an overview of the baseline covariates collected for individuals.

There is an issue with the serum creatinine units for some participants. These have been reported as “umol/L” when in fact it is more likely they are in mg/dL (spike at values reported as umol/L and less than 1, noting that 1 mg/dL = 88.42 umol/L).

Code

all_data %>%
  filter(
    EL_SerumCreatinineUnits == "umol/L",
    EL_SerumCreatinineBlood <= 1.5
  ) %>%
  select(
    EligibilityCode, 
    StudyPatientID, 
    starts_with("EL_Serum")) %>%
  write_csv(file.path(ASCOT_DATA, "derived", "low_creatinine_values.csv"))
ggplot(all_data %>% 
         filter(!is.na(EL_SerumCreatinineUnits)), 
       aes(EL_SerumCreatinine_umolL)) +
  geom_histogram(bins = 50, boundary = 0) +
  facet_wrap( ~ EL_SerumCreatinineUnits) +
  xlim(0, 500)

Figure 5: Histogram of serum creatinine levels at baseline by reported units.

Demographics

Baseline demographics are summarised by intervention in the following table.

Demographics table

sdat <- all_data %>%
    filter(ENR_rec == 1, CAssignment != "C0")
generate_baseline_demographics_table(sdat, format = "html")

Table 5: Baseline demographics for participants randomised into the anticoagulation domain.

	Anticoagulation
Variable	C1 (n = 620)	C2 (n = 620)	C3 (n = 285)	C4 (n = 50)	Overall (n = 1575)
Age (years), Median (IQR)	49 (37, 60)	48 (37, 61)	51 (38, 62)	58 (46, 69)	49 (37, 61)
Sex
Male, n (\%)	361 (58)	392 (63)	158 (55)	25 (50)	936 (59)
Female, n (\%)	259 (42)	228 (37)	127 (45)	25 (50)	639 (41)
Weight (kg)
Median, (IQR)	68 (62, 76)	70 (62, 77)	68 (62, 76)	68 (57, 80)	69 (62, 76)
Missing, n (\%)	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)
Vaccinated1
Yes, n (\%)	194 (31)	222 (36)	42 (15)	27 (54)	485 (31)
Missing, n (\%)	32 (5)	22 (4)	29 (10)	0 (0)	83 (5)
Ethnicity
Indian, n (\%)	500 (81)	522 (84)	277 (97)	4 (8)	1303 (83)
Asian, n (\%)	20 (3)	12 (2)	1 (0)	10 (20)	43 (3)
European, n (\%)	23 (4)	18 (3)	4 (1)	4 (8)	49 (3)
Maori, n (\%)	3 (0)	4 (1)	0 (0)	3 (6)	10 (1)
Pacific Islander, n (\%)	13 (2)	13 (2)	2 (1)	3 (6)	31 (2)
African, n (\%)	1 (0)	0 (0)	1 (0)	0 (0)	2 (0)
Aboriginal, n (\%)	0 (0)	1 (0)	0 (0)	1 (2)	2 (0)
Latin American, n (\%)	0 (0)	1 (0)	0 (0)	0 (0)	1 (0)
Middle Eastern, n (\%)	12 (2)	12 (2)	0 (0)	0 (0)	24 (2)
Other, n (\%)	46 (7)	29 (5)	0 (0)	23 (46)	98 (6)
Unknown, n (\%)	8 (1)	9 (1)	0 (0)	3 (6)	20 (1)
Smoking
Current, n (\%)	17 (3)	22 (4)	3 (1)	5 (10)	47 (3)
Former, n (\%)	76 (12)	53 (9)	15 (5)	14 (28)	158 (10)
Never, n (\%)	527 (85)	545 (88)	267 (94)	31 (62)	1370 (87)
Missing, n (\%)	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)
1 Site LUD does not have ethics approval for collection of vaccination status and accounts for most missingness

Co-morbidities

Baseline co-morbidities are summarised by anti-coagulation intervention in the following table.

Co-morbidities table

sdat <- all_data %>%
    filter(ENR_rec == 1, CAssignment != "C0")
generate_baseline_comorbidities_table(sdat, format = "html")

Table 6: Baseline co-morbidities for participants randomised into then anticoagulation domain.

	Anticoagulation
Comorbidity	C1 (n = 620)	C2 (n = 620)	C3 (n = 285)	C4 (n = 50)	Overall (n = 1575)
None, n (\%)	367 (59.2)	381 (61.5)	166 (58.2)	19 (38.0)	933 (59.2)
Hypertension, n (\%)	152 (24.5)	142 (22.9)	70 (24.6)	14 (28.0)	378 (24.0)
Diabetes, n (\%)	145 (23.4)	141 (22.7)	79 (27.7)	11 (22.0)	376 (23.9)
Obesity, n (\%)	25 (4.0)	24 (3.9)	3 (1.1)	5 (10.0)	57 (3.6)
Asthma, n (\%)	19 (3.1)	16 (2.6)	6 (2.1)	4 (8.0)	45 (2.9)
Chronic lung disease, n (\%)	16 (2.6)	13 (2.1)	1 (0.4)	7 (14.0)	37 (2.3)
Chronic cardiac disease, n (\%)	11 (1.8)	15 (2.4)	1 (0.4)	2 (4.0)	29 (1.8)
Obstructive sleep apnoea, n (\%)	3 (0.5)	3 (0.5)	2 (0.7)	0 (0.0)	8 (0.5)
Iatrogenic immunosuppression, n (\%)	1 (0.2)	6 (1.0)	0 (0.0)	0 (0.0)	7 (0.4)
Chronic kidney disease, n (\%)	0 (0.0)	5 (0.8)	1 (0.4)	0 (0.0)	6 (0.4)
Malignant neoplasm, n (\%)	1 (0.2)	2 (0.3)	0 (0.0)	1 (2.0)	4 (0.3)
Moderate or severe liver disease, n (\%)	2 (0.3)	1 (0.2)	0 (0.0)	0 (0.0)	3 (0.2)
Dialysis, n (\%)	0 (0.0)	1 (0.2)	0 (0.0)	0 (0.0)	1 (0.1)
HIV infection, n (\%)	1 (0.2)	0 (0.0)	0 (0.0)	0 (0.0)	1 (0.1)
Dementia, n (\%)	0 (0.0)	0 (0.0)	0 (0.0)	0 (0.0)	0 (0.0)
Missing, n (\%)	0 (0.0)	0 (0.0)	0 (0.0)	0 (0.0)	0 (0.0)

Prognostics

Baseline prognostics are summarised by anti-coagulation intervention in the following table.

Prognostics table

sdat <- all_data %>%
    filter(ENR_rec == 1, CAssignment != "C0")
generate_baseline_prognostics_table(sdat, format = "html")

Table 7: Baseline prognostic variables for participants randomised into anticoagulation domain.

	Anticoagulation
Variable	C1 (n = 620)	C2 (n = 620)	C3 (n = 285)	C4 (n = 50)	Overall (n = 1575)
Was the patient on room air for any of the preceding 24 hours?
Yes, n (\%)	465 (75)	466 (75)	224 (79)	39 (78)	1194 (76)
Missing, n (\%)	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)
Was the patient's GCS < 15?
Yes, n (\%)	63 (10)	65 (10)	6 (2)	2 (4)	136 (9)
Missing, n (\%)	125 (20)	136 (22)	60 (21)	0 (0)	321 (20)
Peripheral oxygen saturation (SpO2) on room air (Lowest)
Median (IQR)	95 (94, 97)	96 (94, 97)	96 (94, 97)	94 (92, 96)	96 (94, 97)
Missing, n (\%)	154 (25)	151 (24)	56 (20)	10 (20)	371 (24)
Highest respiratory rate (breaths/minute)
Median (IQR)	22 (21, 26)	22 (21, 26)	22 (20, 26)	22 (20, 24)	22 (21, 26)
Missing, n (\%)	0 (0)	1 (0)	0 (0)	0 (0)	1 (0)
Highest recorded Urea in the last 24 hours (mmol/L)
Median (IQR)	4 (3, 5)	5 (4, 6)	4 (3, 6)	4 (3, 6)	4 (3, 6)
Missing, n (\%)	33 (5)	35 (6)	17 (6)	1 (2)	86 (5)
Highest recorded CRP in the last 24 hours (mg/L)
Median (IQR)	71 (37, 190)	75 (38, 220)	77 (44, 223)	68 (33, 129)	73 (38, 200)
Missing, n (\%)	79 (13)	62 (10)	20 (7)	29 (58)	190 (12)
APTT\\textsuperscript{1}
Median (IQR)	33 (29, 36)	33 (30, 36)	32 (28, 37)	33 (28, 38)	33 (29, 36)
Missing, n (\%)	437 (70)	445 (72)	197 (69)	35 (70)	1114 (71)
INR\\textsuperscript{1}
Mean (SD)	1.19 (0.39)	1.23 (0.58)	1.32 (1.34)	1.12 (0.18)	1.23 (0.72)
Missing, n (\%)	109 (18)	109 (18)	49 (17)	7 (14)	274 (17)
Fibrinogen\\textsuperscript{1} (g/L)
Mean (SD)	5.27 (1.95)	5.20 (1.59)	4.78 (1.40)	6.49 (1.52)	5.18 (1.69)
Missing, n (\%)	570 (92)	561 (90)	244 (86)	42 (84)	1417 (90)
Prothrombin time\\textsuperscript{1} (sec)
Median (IQR)	14 (13, 17)	14 (13, 17)	15 (13, 16)	13 (12, 14)	14 (13, 16)
Missing, n (\%)	199 (32)	208 (34)	118 (41)	10 (20)	535 (34)
Taking aspirin
Yes, n (\%)	20 (3)	26 (4)	2 (1)	3 (6)	51 (3)
Missing, n (\%)	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)
1 For APTT, INR, Fibrinogen, and Prothrombin only at least one required.

Age

Histogram of age

all_data %>%
  filter(ENR_rec == 1) %>%
  ggplot(., aes(AgeAtEntry)) + 
  geom_histogram(
    breaks = c(18, seq(20, 100, 5)), 
    colour = "white", 
    closed="left") +
  labs(
    x = "Age at randomisation (5-year bins, 30 to 34, 35 to 39, etc.)", 
    y = "Count") +
  scale_x_continuous(breaks = seq(20, 95, 5))

Figure 6: Distribution of age

Histogram of age by anti-coagulation intervention

p <- all_data %>%
  filter(ENR_rec == 1) %>%
  ggplot(., aes(AgeAtEntry)) + 
  facet_wrap( ~ CAssignment, scales = "free_y", ncol = 5) +
  geom_histogram(
    breaks = c(18, seq(20, 100, 5)), 
    colour = "white", 
    closed="left") +
  labs(
    x = "Age at randomisation (5-year bins, 30 to 34, 35 to 39, etc.)", 
    y = "Count") +
  scale_x_continuous(breaks = seq(20, 95, 5))
ggplotly(p, width = 1700, height = 400)

Figure 7: Distribution of age by anti-coagulation intervention